@inproceedings{cho-etal-2018-hashcount,
title = "{H}ash{C}ount at {S}em{E}val-2018 Task 3: Concatenative Featurization of Tweet and Hashtags for Irony Detection",
author = "Cho, Won Ik and
Kang, Woo Hyun and
Kim, Nam Soo",
editor = "Apidianaki, Marianna and
Mohammad, Saif M. and
May, Jonathan and
Shutova, Ekaterina and
Bethard, Steven and
Carpuat, Marine",
booktitle = "Proceedings of the 12th International Workshop on Semantic Evaluation",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S18-1089",
doi = "10.18653/v1/S18-1089",
pages = "546--552",
abstract = "This paper proposes a novel feature extraction process for SemEval task 3: Irony detection in English tweets. The proposed system incorporates a concatenative featurization of tweet and hashtags, which helps distinguishing between the irony-related and the other components. The system embeds tweets into a vector sequence with widely used pretrained word vectors, partially using a character embedding for the words that are out of vocabulary. Identification was performed with BiLSTM and CNN classifiers, achieving F1 score of 0.5939 (23/42) and 0.3925 (10/28) each for the binary and the multi-class case, respectively. The reliability of the proposed scheme was verified by analyzing the Gold test data, which demonstrates how hashtags can be taken into account when identifying various types of irony.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cho-etal-2018-hashcount">
<titleInfo>
<title>HashCount at SemEval-2018 Task 3: Concatenative Featurization of Tweet and Hashtags for Irony Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Won</namePart>
<namePart type="given">Ik</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Woo</namePart>
<namePart type="given">Hyun</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nam</namePart>
<namePart type="given">Soo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th International Workshop on Semantic Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">May</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper proposes a novel feature extraction process for SemEval task 3: Irony detection in English tweets. The proposed system incorporates a concatenative featurization of tweet and hashtags, which helps distinguishing between the irony-related and the other components. The system embeds tweets into a vector sequence with widely used pretrained word vectors, partially using a character embedding for the words that are out of vocabulary. Identification was performed with BiLSTM and CNN classifiers, achieving F1 score of 0.5939 (23/42) and 0.3925 (10/28) each for the binary and the multi-class case, respectively. The reliability of the proposed scheme was verified by analyzing the Gold test data, which demonstrates how hashtags can be taken into account when identifying various types of irony.</abstract>
<identifier type="citekey">cho-etal-2018-hashcount</identifier>
<identifier type="doi">10.18653/v1/S18-1089</identifier>
<location>
<url>https://aclanthology.org/S18-1089</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>546</start>
<end>552</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HashCount at SemEval-2018 Task 3: Concatenative Featurization of Tweet and Hashtags for Irony Detection
%A Cho, Won Ik
%A Kang, Woo Hyun
%A Kim, Nam Soo
%Y Apidianaki, Marianna
%Y Mohammad, Saif M.
%Y May, Jonathan
%Y Shutova, Ekaterina
%Y Bethard, Steven
%Y Carpuat, Marine
%S Proceedings of the 12th International Workshop on Semantic Evaluation
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F cho-etal-2018-hashcount
%X This paper proposes a novel feature extraction process for SemEval task 3: Irony detection in English tweets. The proposed system incorporates a concatenative featurization of tweet and hashtags, which helps distinguishing between the irony-related and the other components. The system embeds tweets into a vector sequence with widely used pretrained word vectors, partially using a character embedding for the words that are out of vocabulary. Identification was performed with BiLSTM and CNN classifiers, achieving F1 score of 0.5939 (23/42) and 0.3925 (10/28) each for the binary and the multi-class case, respectively. The reliability of the proposed scheme was verified by analyzing the Gold test data, which demonstrates how hashtags can be taken into account when identifying various types of irony.
%R 10.18653/v1/S18-1089
%U https://aclanthology.org/S18-1089
%U https://doi.org/10.18653/v1/S18-1089
%P 546-552
Markdown (Informal)
[HashCount at SemEval-2018 Task 3: Concatenative Featurization of Tweet and Hashtags for Irony Detection](https://aclanthology.org/S18-1089) (Cho et al., SemEval 2018)
ACL